CN110498314A - Health evaluating method, system, electronic equipment and the storage medium of elevator car door system - Google Patents

Abstract

The invention discloses health evaluating method, system, electronic equipment and the storage medium of a kind of elevator car door system, the health evaluating method includes: corresponding first history data when obtaining elevator car door system normal operating condition；Obtain the current operating data of elevator car door system in the current state of operation；Obtain first object model and the second object module；Obtain the first registration between current operating conditions and normal operating condition；The corresponding health degree of current operating situation of elevator car door system is determined according to the first registration.The multidimensional operation data for monitoring elevator car door system in the present invention simultaneously realizes the real-time assessment to the health status of elevator car door system based on gauss hybrid models, to improve the assessment accuracy of the health status of elevator car door system；Additionally, it is provided the health status alarming mechanism of elevator car door system, can remind in time user or maintenance personal to carry out maintenance measure appropriate in advance to elevator door, and then avoid elevator door and break down.

Description

Health evaluating method, system, electronic equipment and the storage medium of elevator car door system

Technical field

The present invention relates to elevator management technical field, in particular to the health evaluating method of a kind of elevator car door system is System, electronic equipment and storage medium.

Background technique

With increasing for skyscraper, elevator increasingly becomes the indispensable vertical transport tool of people.Through excessive Year development, state's elevator ownership increases substantially and day hastens towards saturation.With the accumulation of elevator runing time, elevator generates failure Probability can also significantly improve therewith.Since the switch motion of elevator door-motor is very frequent, elevator car door system is easily lead in this way It breaks down, elevator car door system Frequent Troubles have become the main component part of elevator accident, wherein 80% or more The elevator accident of elevator faults and 70% or more is caused because elevator car door system goes wrong；Once elevator car door system Breaking down, it will cause unthinkable serious consequences, it is therefore desirable to be had in time to the operating status of elevator car door system Effect monitoring.

Currently, elevator both domestic and external by the treatment process that maintenance personnel safeguards elevator car door system include: 1) when After door machine breaks down, the source of trouble, maintenance or replacement trouble unit are determined；2) regardless of whether door system failure, fixed cycle occurs By defined process to its putting maintenance into practice.There are the following problems for maintenance mode in this way: when there are a degree of for elevator car door system Performance degradation cannot be found in time, not safeguarded to it；Or no matter how actual conditions are blindly safeguarded all in accordance with unified flow, In this way it is possible to leading to door machine accident, and will cause it is unnecessary stop ladder and maintenance cost, cost of labor it is higher.

In addition, there are also the real-time current signals based on current sensor acquisition elevator car door system at present, by judging the reality When current signal whether within the scope of normality threshold, assessed with this whether elevator car door system breaks down, in this way safeguard There is the problems such as assessment accuracy is lower in mode.

Summary of the invention

The technical problem to be solved by the present invention is to the assessment modes in the prior art to the health status of elevator car door system to deposit In the assessment lower defect of accuracy, and it is an object of the present invention to provide a kind of health evaluating method of elevator car door system, system, electronics are set Standby and storage medium.

The present invention is to solve above-mentioned technical problem by following technical proposals:

The present invention provides a kind of health evaluating method of elevator car door system, and the health evaluating method includes:

S1. it obtains elevator car door system and is in corresponding first history when normal operating condition within the history samples period Operation data；

S2. the current operation number in the present sample period of the elevator car door system in the current state of operation is obtained According to；

S3. mesh is input to using first history data and the current operating data as training parameter respectively Mark model is trained, and is obtained for characterizing the first object model of the normal operation of the elevator car door system and being used for Characterize the second object module of the current operating situation of the elevator car door system；

S4. according to the first object model and second object module obtain the current operating conditions with it is described The first registration between normal operating condition；

S5. the corresponding health degree of current operating situation of the elevator car door system is determined according to first registration；

Wherein, first registration is positively correlated with the health degree.

Preferably, the first object model is mixed for the first Gauss when the object module includes gauss hybrid models Molding type, second object module are the second gauss hybrid models；

Step S4 includes:

S41. the current fortune is calculated according to first gauss hybrid models and second gauss hybrid models The first registration between row state and the normal operating condition.

Preferably, when first history data includes the holding duration or the holding of door closing procedure of door opening process When duration and mechanical energy average value, step S1 is specifically included:

S11. the elevator car door system is obtained in the total degree of the inward swinging door of history preset time period or shutdown and described Duration is kept to meet first number of enabling or the shutdown of preset duration range；

S12. the ratio of first number and the total degree is calculated；

S13. the ratio is judged whether more than the first given threshold, if being more than, it is determined that the preset time period is to go through History intermediary time period；

S14. history target time section is obtained according to the corresponding mechanical energy average value of each history intermediary time period；

S15. using the corresponding operation data of sampling time point each in the history target time section as in normal fortune Corresponding first history data when row state.

Preferably, step S14 includes:

The corresponding mechanical energy average value of each history intermediary time period is ranked up according to size, described in selection Corresponding history intermediary time period is as the history target time section when mechanical energy average value minimum；

Wherein, the health degree of the operating status of the size and elevator car door system of the mechanical energy average value It is negatively correlated；And/or

The history preset time period is as unit of day.

Preferably, after step S15, before step S3 further include:

Corresponding first data matrix is obtained according to first history data；

First data matrix is standardized, fisrt feature matrix is obtained；

Corresponding second data matrix is obtained according to the current operating data；

Second data matrix is standardized, second characteristic matrix is obtained；

Step S3 further include:

Respectively using the fisrt feature matrix and the second characteristic matrix as training parameter, it is input to the target Model is trained, and is obtained the first object model for characterizing the normal operation of the elevator car door system and is used for table Levy the second object module of the current operating situation of the elevator car door system.

Preferably, first gauss hybrid models or second gauss hybrid models include:

Wherein, g (x) indicates first gauss hybrid models or second gauss hybrid models, h (x；θ_i) indicate single Gaussian function, x indicate that d ties up the fisrt feature matrix or the second characteristic matrix, and I indicates mixed model quantity, p_iIt indicates The prioritized vector of preset i-th single Gaussian function, meetsθ_iIndicate the model of i-th of single Gaussian function Parameter, the model parameter include average vector μ_iWith covariance matrix σ_i。

Preferably, calculating first registration using following formula in step S41:

Wherein, CV indicates first registration, g₁(x1) first gauss hybrid models, g are indicated₂(x2) institute is indicated The second gauss hybrid models are stated, x1 indicates that the fisrt feature matrix, x2 indicate the second characteristic matrix.

Preferably, the health evaluating method further include:

The operation data of sub-health state and malfunction corresponding first in the history samples period is preset respectively Label and the second label；

After step S5 further include:

The second history run that sub-health state is corresponded in the history samples period is obtained according to first label Data；

The third history run number that malfunction is corresponded in the history samples period is obtained according to second label According to；

According to the corresponding third data matrix of second history data；

The third data matrix is standardized, third feature matrix is obtained；

Corresponding 4th data matrix is obtained according to the third history data；

4th data matrix is standardized, fourth feature matrix is obtained；

It using the third feature matrix as training parameter, is input to gauss hybrid models and is trained, obtain and be used for table Levy the third gauss hybrid models of elevator car door system operating condition under sub-health state；

It using the fourth feature matrix as training parameter, is input to gauss hybrid models and is trained, obtain and be used for table The elevator car door system is levied to nonserviceable the 4th gauss hybrid models of lower operating condition；

The sub-health state is calculated according to first gauss hybrid models and the third gauss hybrid models The second registration between the normal operating condition；

According to first gauss hybrid models and the 4th gauss hybrid models be calculated the malfunction with Third registration between the normal operating condition；

The first early warning value is set according to the maximum value in multiple second registrations；

Wherein, the feelings that enabling or shutdown function of first early warning value for elevator car door system described in early warning reduce Condition；

The second early warning value is set according to the maximum value in multiple third registrations；

Wherein, there is a situation where enablings or shutdown failure for elevator car door system described in early warning for second early warning value.

Preferably, the health evaluating method further include:

Mean filter processing is carried out to first registration using the sliding window of the first width and the second width, is obtained Take corresponding 4th registration of each sampling time point and the 5th registration in the present sample period；

Wherein, first width corresponds to long period, and second width corresponds to short cycle；

When the 4th registration is less than first early warning value, and the 5th registration is greater than or equal to described the When two early warning values, then the first warning information that enabling or shutdown function for characterizing the elevator car door system reduce is generated；

When the 5th registration is less than second early warning value, generates and occur for characterizing the elevator car door system Second warning information of enabling or shutdown failure.

Preferably, first history data, second history data, the third history run number It include in gate-control signal data, current data, energy data, power data and speed data according to, the current operating data At least one.

The present invention also provides a kind of health evaluation system of elevator car door system, the health evaluation system is gone through including first History data acquisition module, current data obtain module, model obtains module, the first registration obtains module and health degree is true Cover half block；

First historical data obtains module for obtaining elevator car door system within the history samples period in normal Corresponding first history data when operating status；

The current data obtains module for obtaining the present sample of the elevator car door system in the current state of operation Current operating data in period；

The model obtain module for respectively using first history data and the current operating data as Training parameter is input to object module and is trained, and obtains the of the normal operation for characterizing the elevator car door system Second object module of one object module and the current operating situation for characterizing the elevator car door system；

First registration obtains module and is used to be obtained according to the first object model and second object module The first registration between the current operating conditions and the normal operating condition；

The health degree determining module is used to determine the current fortune of the elevator car door system according to first registration The corresponding health degree of market condition；

Wherein, first registration is positively correlated with the health degree.

Preferably, the first object model is mixed for the first Gauss when the object module includes gauss hybrid models Molding type, second object module are the second gauss hybrid models；

First registration obtains module and is used for according to first gauss hybrid models and second Gaussian Mixture The first registration between the current operating conditions and the normal operating condition is calculated in model.

Preferably, when first history data includes the holding duration or the holding of door closing procedure of door opening process When duration and mechanical energy average value, it includes number acquiring unit, ratio calculation list that first historical data, which obtains module, Member, judging unit, target time section acquiring unit and historical data acquiring unit；

The number acquiring unit is used to obtain the elevator car door system in the inward swinging door of history preset time period or shutdown Total degree and first number of enabling or the shutdown for keeping duration to meet preset duration range；

The ratio calculation unit is used to calculate the ratio of first number and the total degree；

The judging unit is for judging the ratio whether more than the first given threshold, if being more than, it is determined that described pre- If the period is history intermediary time period；

The target time section acquiring unit is used for average according to the corresponding mechanical energy of each history intermediary time period Value obtains history target time section；

The historical data acquiring unit is used for the corresponding fortune of sampling time point each in the history target time section Row data corresponding first history data when being used as in normal operating condition.

Preferably, the target time section acquiring unit is used for the corresponding machinery of each history intermediary time period Energy average value is ranked up according to size, chooses corresponding history intermediary time period conduct when the mechanical energy average value minimum The history target time section；

Wherein, the health degree of the operating status of the size and elevator car door system of the mechanical energy average value It is negatively correlated；And/or

The history preset time period is as unit of day.

Preferably, the health evaluation system further includes that fisrt feature matrix obtains module and second characteristic matrix acquisition Module；

The fisrt feature matrix obtains module and is used to obtain corresponding first number according to first history data It is standardized according to matrix, and to first data matrix, obtains fisrt feature matrix；

The second characteristic matrix obtains module and is used to obtain corresponding second data square according to the current operating data Battle array, and second data matrix is standardized, obtain second characteristic matrix；

The model obtains module for respectively using the fisrt feature matrix and the second characteristic matrix as training Parameter is input to the object module and is trained, and obtains the of the normal operation for characterizing the elevator car door system Second object module of one object module and the current operating situation for characterizing the elevator car door system.

Preferably, first gauss hybrid models or second gauss hybrid models include:

Wherein, g (x) indicates first gauss hybrid models or second gauss hybrid models, h (x；θ_i) indicate single Gaussian function, x indicate that d ties up the fisrt feature matrix or the second characteristic matrix, and I indicates mixed model quantity, p_iIt indicates The prioritized vector of preset i-th single Gaussian function, meetsθ_iIndicate the model of i-th of single Gaussian function Parameter, the model parameter include average vector μ_iWith covariance matrix σ_i。

Preferably, first registration, which obtains module, calculates first registration using following formula:

Wherein, CV indicates first registration, g₁(x1) first gauss hybrid models, g are indicated₂(x2) institute is indicated The second gauss hybrid models are stated, x1 indicates that the fisrt feature matrix, x2 indicate the second characteristic matrix.

Preferably, the health evaluation system obtains module for label presetting module, the second historical data, third is gone through History data acquisition module, third feature matrix obtain module, fourth feature matrix obtains module, the second registration obtains module, Third registration obtains module and early warning value setting module；

The label presetting module for presetting sub-health state and malfunction in the history samples period respectively Corresponding first label of operation data and the second label；

Second historical data obtains module and is used to be obtained in the history samples period according to first label Second history data of corresponding sub-health state；

The third historical data obtains module and is used to be obtained in the history samples period according to second label The third history data of corresponding malfunction；

The third feature matrix obtains module and is used for according to the corresponding third data square of second history data Battle array, and the third data matrix is standardized, obtain third feature matrix；

The fourth feature matrix obtains module and is used to obtain corresponding 4th number according to the third history data It is standardized according to matrix, and to the 4th data matrix, obtains fourth feature matrix；

The model obtains module and is also used to be input to Gaussian Mixture using the third feature matrix as training parameter Model is trained, and obtains the third Gaussian Mixture for characterizing elevator car door system operating condition under sub-health state Model；

The model obtains module and is also used to be input to Gaussian Mixture using the fourth feature matrix as training parameter Model is trained, and is obtained and is nonserviceabled the 4th Gaussian Mixture mould of lower operating condition for characterizing the elevator car door system Type；

Second registration obtains module and is used for according to first gauss hybrid models and the third Gaussian Mixture The second registration between the sub-health state and the normal operating condition is calculated in model；

The third registration obtains module and is used for according to first gauss hybrid models and the 4th Gaussian Mixture The third registration between the malfunction and the normal operating condition is calculated in model；

The early warning value setting module is used to set the first early warning according to the maximum value in multiple second registrations Value；

Wherein, the feelings that enabling or shutdown function of first early warning value for elevator car door system described in early warning reduce Condition；

The early warning value setting module is also used to set the second early warning according to the maximum value in multiple third registrations Value；

Wherein, there is a situation where enablings or shutdown failure for elevator car door system described in early warning for second early warning value.

Preferably, the health evaluation system includes filtering processing module, the first warning information generation module and the second announcement Alert information generating module；

The filtering processing module is used for using the sliding window of the first width and the second width to first registration Mean filter processing is carried out, corresponding 4th registration of each sampling time point in the present sample period and the are obtained Five registrations；

Wherein, first width corresponds to long period, and second width corresponds to short cycle；

The first warning information generation module is used to be less than first early warning value, and institute when the 4th registration When stating the 5th registration more than or equal to second early warning value, then generate enabling for characterizing the elevator car door system or The first warning information that person's shutdown function reduces；

The second warning information generation module is used for when the 5th registration is less than second early warning value, raw At the second warning information that enabling or shutdown failure occur for characterizing the elevator car door system.

Preferably, first history data, second history data, the third history run number It include in gate-control signal data, current data, energy data, power data and speed data according to, the current operating data At least one.

The present invention also provides a kind of electronic equipment, including memory, processor and storage on a memory and can handled The computer program run on device, the processor realize that the health of above-mentioned elevator car door system is commented when executing computer program Estimate method.

The present invention also provides a kind of computer readable storage mediums, are stored thereon with computer program, the computer journey The step of health evaluating method of above-mentioned elevator car door system is realized when sequence is executed by processor.

The positive effect of the present invention is that:

In the present invention, first for characterizing normal operation is established by the multidimensional data based on elevator car door system Gauss hybrid models model and the second gauss hybrid models model for characterizing current operating situation, and then obtain current fortune The first registration between row state and normal operating condition assesses the current fortune of elevator car door system according to first registration The corresponding health degree of market condition realizes real-time, comprehensive monitoring and analysis, to improve the health status of elevator car door system Assessment accuracy；And without label data (being not necessarily to manual intervention), to reduce cost of labor；In addition, additionally providing electricity The health status alarming mechanism of terraced door system can remind user or maintenance personal to carry out elevator door in advance appropriate in time Maintenance measure, and then avoid elevator door and break down.

Detailed description of the invention

Fig. 1 is the flow chart of the health evaluating method of the elevator car door system of the embodiment of the present invention 1.

Fig. 2 is the first pass figure of the health evaluating method of the elevator car door system of the embodiment of the present invention 2.

Fig. 3 is the second flow chart of the health evaluating method of the elevator car door system of the embodiment of the present invention 2.

Fig. 4 is the flow chart of the health evaluating method of the elevator car door system of the embodiment of the present invention 3.

Fig. 5 is the module diagram of the health evaluation system of the elevator car door system of the embodiment of the present invention 4.

Fig. 6 is the first module diagram of the health evaluation system of the elevator car door system of the embodiment of the present invention 5.

Fig. 7 is the second module diagram of the health evaluation system of the elevator car door system of the embodiment of the present invention 5.

Fig. 8 is the module diagram of the health evaluation system of the elevator car door system of the embodiment of the present invention 6.

Fig. 9 is the structural representation of the electronic equipment of the health evaluating method of the realization elevator car door system of the embodiment of the present invention 7 Figure.

Specific embodiment

The present invention is further illustrated below by the mode of embodiment, but is not therefore limited the present invention to described Among scope of embodiments.

Embodiment 1

As shown in Figure 1, the health evaluating method of the elevator car door system of the present embodiment includes:

Corresponding first goes through when S101, acquisition elevator car door system are in normal operating condition within the history samples period History operation data；

S102, the current operating data in the present sample period of acquisition elevator car door system in the current state of operation；

Wherein, the first history data, current operating data include but is not limited to gate-control signal data, electric current number According to, energy data, power data and speed data, the i.e. car movement data of multiple dimensions of comprehensive monitoring elevator car door system, More fully assess the operating status of elevator car door system；And it can guarantee not allowing to be also easy to produce over-fitting when model training.

S103, respectively using the first history data and current operating data as training parameter, be input to object module It is trained, obtains for characterizing the first object model of the normal operation of elevator car door system and for characterizing elevator door Second object module of the current operating situation of system；

S104, obtained according to first object model and the second object module current operating conditions and normal operating condition it Between the first registration；

S105, the corresponding health degree of current operating situation that elevator car door system is determined according to the first registration；

Wherein, the first registration is positively correlated with health degree.

Evaluation process in the present embodiment is not necessarily to manual intervention, i.e. the degree of automation is higher, thereby reduce manually at This.

In the present embodiment, for characterizing normal operation is established by multidimensional data based on elevator car door system One gauss hybrid models model and the second gauss hybrid models model for characterizing current operating situation, and then obtain current The first registration between operating status and normal operating condition assesses the current of elevator car door system according to first registration The corresponding health degree of operating condition is realized more while realizing in real time to the assessment of the health status of elevator car door system Comprehensive monitoring and analysis, improve the assessment accuracy of the health status of elevator car door system.

Embodiment 2

The health evaluating method of the elevator car door system of the present embodiment is the further improvement to embodiment 1, specifically:

As shown in Fig. 2, when the first history data include door opening process holding duration or door closing procedure holding when When long and mechanical energy average value, step S101 is specifically included:

S10101, when obtaining elevator car door system in the total degree of the inward swinging door of history preset time period or shutdown, and keeping First number of long enabling or the shutdown for meeting preset duration range；

Wherein, history preset time period is as unit of day.

S10102, the ratio for calculating first number and total degree；

S10103, ratio is judged whether more than the first given threshold, if being more than, it is determined that preset time period is in history Between the period；

S10104, history target time section is obtained according to the corresponding mechanical energy average value of each history intermediary time period；

Specifically, the corresponding mechanical energy average value of each history intermediary time period is ranked up according to size, is selected Corresponding history intermediary time period is as history target time section when taking mechanical energy average value minimum.

Wherein, the health degree of the operating status of the size and elevator car door system of mechanical energy average value is negatively correlated；

S10105, it is transported using the corresponding operation data of sampling time point each in history target time section as in normal Corresponding first history data when row state is oriented based on original no label history data Automatic-searching Normal condition data in the history samples period.

As shown in figure 3, after step S102, before step S103 further include:

S1021, corresponding first data matrix is obtained according to the first history data；

First data matrix is standardized, fisrt feature matrix is obtained；

S1022, corresponding second data matrix is obtained according to current operating data；

Second data matrix is standardized, second characteristic matrix is obtained；

Wherein, corresponding to sampling time point each in each sampling time section in conjunction with expertise and feature extraction algorithm All operation datas carry out feature extraction and Feature Conversion processing, retain setting quantity characteristic parameter, such as following 15 spies Sign parameter: Q shaft current adds up electric energy, D shaft current adds up the sum of electric energy, velocity error, (velocity error square and velocity error The position of the positive maximum value appearance of the positive maximum value of the ratio of count value, velocity error, the negative maximum value of velocity error, velocity error, speed The position of degree error minus maximum value appearance, currently terminates the sum of initial position, Iq positive value, Iq negative value at current state initial position The sum of, the sum of Id positive value, the sum of Id negative value, mechanical energy average value etc..

The operating status for obtaining elevator car door system in the history samples period is one day most normal, and obtains in this day The first data matrix X1 of each corresponding operation data (15 characteristic parameters) formation of sampling time point；When obtaining present sample Between in section corresponding operation data (the 15 characteristic parameters) current operating data of each sampling time point form the second data matrix X2；

First data matrix X1 and the second data matrix X2 are standardized, respectively obtain corresponding One eigenmatrix and second characteristic matrix are specifically standardized using following formula:

X=(X- μ)/σ

Wherein, x indicates that fisrt feature matrix or second characteristic matrix, X indicate the first data matrix or the second data square Battle array, μ indicate that average vector, σ indicate covariance matrix.

Step S103 includes:

S1031, respectively using fisrt feature matrix and second characteristic matrix as training parameter, be input to object module into Row training, obtains for characterizing the first object model of the normal operation of elevator car door system and for characterizing elevator door system Second object module of the current operating situation of system.

When object module includes gauss hybrid models, first object model is the first gauss hybrid models, the second target Model is the second gauss hybrid models.Wherein, object module can also include that other any can be realized for characterizing elevator door The model of the operating condition of system.

Step S104 includes:

S1041, be calculated according to the first gauss hybrid models and the second gauss hybrid models current operating conditions with just The first registration between normal operating status.

Specifically: the first gauss hybrid models or the second gauss hybrid models include:

Wherein, g (x) indicates the first gauss hybrid models or the second gauss hybrid models, h (x；θ_i) indicate single Gaussian function Number, x indicate that d dimension fisrt feature matrix or second characteristic matrix, I indicate mixed model quantity, p_iIndicate preset i-th single high The prioritized vector of this function meetsθ_iIndicate the model parameter of i-th of single Gaussian function, model parameter packet Include average vector μ_iWith covariance matrix σ_i。

Specifically, using EM (expectation maximization) algorithm to parameter θ_iEstimated, specific solution procedure is as follows:

(1) random initializtion model parameter θ；

(2) Bayes' theorem is used, data characteristics vector x is used_nIt is general with the posteriority of "current" model parameter θ computation model i Rate, specific formula is as follows:

(3) the maximum likelihood revaluation of model coefficient

By repeating step (2) and step (3) in an iterative process, calculating converges to a stable solution, the stable solution pair Maximum likelihood solution is answered, and then obtains convergent mean value, covariance matrix and preposition vector.

In addition, the selection of mixed model quantity I is come using BIC (Bayesian Information) criterion algorithm in gauss hybrid models It determines, specific formula is as follows:

Wherein, H_jIndicate that j-th candidates model, D indicate training characteristics,Indicate j-th candidates The max log likelihood function of model, k indicate the number for being estimated parameter, and n indicates the size of feature, and final establish has minimum Best gauss hybrid models (i.e. the first gauss hybrid models) g of bayesian information criterion score₁(x), the gauss hybrid models For the model of most accurate characterization elevator door normal operation.

The first registration is calculated using following formula in step S1041:

Wherein, CV indicates the first registration, g₁(x1) the first gauss hybrid models, g are indicated₂(x2) indicate that the second Gauss is mixed Molding type, x1 indicate that fisrt feature matrix, x2 indicate second characteristic matrix.

CV value range is 0-1, and the CV value is higher, then it represents that the current operating situation of elevator car door system is closer to normal State；Conversely, the CV value is lower, then it represents that the current operating situation of elevator car door system is further away from normal condition, it may occur however that certain It is a little to degenerate, need real-time maintenance measure appropriate.

In the present embodiment, by establishing for characterizing the first gauss hybrid models model of normal operation and being used for Characterize the second gauss hybrid models model of current operating situation, so obtain current operating conditions and normal operating condition it Between the first registration, according to first registration assess elevator car door system the corresponding health degree of current operating situation, knot Multidimensional data is closed, more comprehensive monitoring and analysis are realized, to improve the assessment accuracy of the health status of elevator car door system； And without label data (being not necessarily to manual intervention), to reduce cost of labor.

Embodiment 3

As shown in figure 4, the health evaluating method of the elevator car door system of the present embodiment is the further improvement to embodiment 2, Specifically:

After step S105 further include:

S106, the operation data of sub-health state and malfunction corresponding the in the history samples period is preset respectively One label and the second label；

Wherein, the process for presetting label is by setting pair between sub-health state, malfunction and corresponding operation data The process that should be related to.

Sub-health state includes but is not limited to the case where slider wear, guide rail cause frictional force to increase there are foreign matter.

Malfunction includes but is not limited to that switch gate is not in place, gate does not drive hall door, rail friction acutely to cause to switch The case where door velocity anomaly.

S107, the second history run number that sub-health state is corresponded in the history samples period is obtained according to the first label According to；

S108, the third history data that malfunction is corresponded in the history samples period is obtained according to the second label；

Wherein, the second history data, third history data include but is not limited to gate-control signal data, electricity Flow data, energy data, power data and speed data.

S109, according to the corresponding third data matrix of the second history data；

Third data matrix is standardized, third feature matrix is obtained；

S1010, corresponding 4th data matrix is obtained according to third history data；

4th data matrix is standardized, fourth feature matrix is obtained；

S1011, using third feature matrix as training parameter, be input to gauss hybrid models and be trained, acquisition is used for Characterize the third gauss hybrid models of elevator car door system operating condition under sub-health state；

S1012, using fourth feature matrix as training parameter, be input to gauss hybrid models and be trained, acquisition is used for Characterization elevator car door system is nonserviceabled the 4th gauss hybrid models of lower operating condition；

S1013, sub-health state and normal is calculated according to the first gauss hybrid models and third gauss hybrid models The second registration between operating status；

S1014, malfunction and normal fortune are calculated according to the first gauss hybrid models and the 4th gauss hybrid models Third registration between row state；

S1015, the first early warning value is set according to the maximum value in multiple second registrations；

Wherein, the case where enabling or shutdown function of first early warning value for early warning elevator car door system reduce；

S1016, the second early warning value is set according to the maximum value in multiple third registrations；

Wherein, there is a situation where enablings or shutdown failure for early warning elevator car door system for the second early warning value.

Specifically, the corresponding third gauss hybrid models of each sampling time point under sub-health state:

g_u1(x_u1)、g_u2(x_u2)···

According to each third gauss hybrid models and the first gauss hybrid models calculate separately to obtain sub-health state with just Multiple second registrations between normal operating status:

CV_u1,CV_u2····

Corresponding 4th gauss hybrid models of each sampling time point under malfunction:

g_d1(x_d1)、g_d2(x_d2)···

Calculate separately to obtain malfunction and normal according to each 4th gauss hybrid models and the first gauss hybrid models Multiple third registrations between operating status:

CV_d1,CV_d2···

CV_T1=max (CV_d1,CV_d2······)

CV_T2=max (CV_u1,CV_u2······)

According to CV_T1The first early warning value is determined, according to CV_T2Determine the second early warning value.

S1017, mean filter processing is carried out to the first registration using the sliding window of the first width and the second width, Obtain corresponding 4th registration of each sampling time point and the 5th registration in the present sample period；

Wherein, the first width corresponds to long period (such as n value 500), and the second width corresponds to short cycle (such as n value 5).

S1018, when the 4th registration is less than the first early warning value, and the 5th registration is greater than or equal to the second early warning value, Then generate the first warning information that enabling or shutdown function for characterizing elevator car door system reduce；

When the 5th registration is less than the second early warning value, generates and event of opening the door or close the door occurs for characterizing elevator car door system Second warning information of barrier.

Analyze to obtain the feelings that enabling or shutdown failure occur for elevator car door system under sub-health state by the 4th registration Condition；Analyze to obtain the feelings that enabling or the reduction of shutdown function of elevator car door system occur under malfunction by the 5th registration Condition, to be alerted in time, in order to which personnel carry out malfunction elimination and processing in time.

Illustrate below with reference to specific example:

1) elevator car door system daily corresponding operation data within half a year in past is obtained, feature is carried out to operation data and is mentioned It takes and Feature Conversion, retains 15 characteristic parameters；

2) it obtains the open the door daily holding duration of total degree and door opening process of elevator car door system and is equal to preset duration (such as 377) door opening times；

3) ratio for calculating door opening times and total degree chooses every day on the corresponding date that ratio is greater than 95%, then Each mechanical energy average value corresponding to these days is ranked up, and is chosen mechanical energy average value the smallest one day and is used as mechanical energy Average value ran one day most normal within half a year in past, it is assumed that is 2019-03-12, it is each to obtain this day 2019-03-12 The corresponding time series of sampling time point (i.e. the first data matrix) X1；

4) corresponding second data of each sampling time point in the present sample period under current operating conditions are obtained Matrix X2；

5) the first data matrix X1 and the second data matrix X2 are standardized, are respectively obtained corresponding Fisrt feature matrix x1 and second characteristic matrix x2；

6) Gaussian Mixture mould is input to using fisrt feature matrix x1 and second characteristic matrix x2 as training parameter respectively Type is trained, and obtains the first gauss hybrid models g for characterizing the normal operation of elevator car door system₁(x1) it and uses In the second gauss hybrid models g of the current operating situation of characterization elevator car door system₂(x2)。

7) according to the first gauss hybrid models g₁(x1) and the second gauss hybrid models g₂(x2) current operation is calculated The first registration CV between state and normal operating condition, such as obtain corresponding first weight of current a certain sampling time point Right CV=0.5932.

Obtain elevator car door system third gauss hybrid models of operating condition and its corresponding multiple under sub-health state Second registration:

g_u1(x_u1)、g_u2(x_u2)···；CV_u1,CV_u2····

Elevator car door system is obtained to nonserviceable the 4th gauss hybrid models of lower operating condition:

g_d1(x_d1)、g_d2(x_d2)···；CV_d1,CV_d2···

CV_T1=max (CV_d1,CV_d2)=0.2541；

CV_T2=max (CV_u1,CV_u2)=0.7806；

According to CV_T1Determine that the first early warning value is 0.3, according to CV_T2Determine that the second early warning value is 0.8.

8) different in width (n is used to the corresponding first registration CV of each sampling time point in the present sample period =5 and n=500) mean filter is filtered and obtains corresponding 4th registration CV_SAnd CV_L；

9) work as CV_LLess than 0.8 and CV_SWhen more than or equal to 0.3, then generate for characterize elevator car door system enabling or The first warning information that shutdown function reduces；Work as CV_SWhen less than 0.3, then generate for characterize elevator car door system occur open the door or Second warning information of shutdown failure.

In addition, the evaluation process of the health status of the door closing procedure of elevator car door system is similar to the strong of above-mentioned door opening process The evaluation process of health state, therefore be not described in more detail here.

In the present embodiment, by establishing for characterizing the first gauss hybrid models model of normal operation and being used for Characterize the second gauss hybrid models model of current operating situation, so obtain current operating conditions and normal operating condition it Between the first registration, according to first registration assess elevator car door system the corresponding health degree of current operating situation, knot Multidimensional data is closed, more comprehensive monitoring and analysis are realized, to improve the assessment accuracy of the health status of elevator car door system； And without label data (being not necessarily to manual intervention), to reduce cost of labor；Additionally, it is provided the health of elevator car door system State alarming mechanism can remind in time user or maintenance personal to carry out maintenance measure appropriate in advance to elevator door, and then keep away Exempt from elevator door to break down.

Embodiment 4

As shown in figure 5, the health evaluation system of the elevator car door system of the present embodiment includes that the first historical data obtains module 1, current data obtains module 2, model obtains module 3, the first registration obtains module 4 and health degree determining module 5.

First historical data obtains module 1 for obtaining elevator car door system within the history samples period in normal fortune Corresponding first history data when row state；

Current data obtains module 2 for obtaining the present sample period of elevator car door system in the current state of operation Interior current operating data；

Wherein, the first history data, current operating data include but is not limited to gate-control signal data, electric current number According to, energy data, power data and speed data, the i.e. car movement data of multiple dimensions of comprehensive monitoring elevator car door system, More fully assess the operating status of elevator car door system；And it can guarantee not allowing to be also easy to produce over-fitting when model training.

Model obtains module 3 and is used for respectively using the first history data and current operating data as training parameter, defeated Enter to object module and be trained, obtains the first object model and use for characterizing the normal operation of elevator car door system In the second object module of the current operating situation of characterization elevator car door system；

First registration obtains module 4 and is used to obtain current operation shape according to first object model and the second object module The first registration between state and normal operating condition；

Health degree determining module 5 is used to determine that the current operating situation of elevator car door system is corresponding according to the first registration Health degree；

Wherein, the first registration is positively correlated with health degree.

Evaluation process in the present embodiment is not necessarily to manual intervention, i.e. the degree of automation is higher, thereby reduce manually at This.

In the present embodiment, by establishing for characterizing the first gauss hybrid models model of normal operation and being used for Characterize the second gauss hybrid models model of current operating situation, so obtain current operating conditions and normal operating condition it Between the first registration, according to first registration assess elevator car door system the corresponding health degree of current operating situation, In While realization in real time to the assessment of the health status of elevator car door system, in conjunction with multidimensional data, realizes more comprehensive monitoring and divide Analysis, improves the assessment accuracy of the health status of elevator car door system.

Embodiment 5

The health evaluation system of the elevator car door system of the present embodiment is the further improvement to embodiment 4, specifically:

As shown in fig. 6, when the first history data include door opening process holding duration or door closing procedure holding when When long and mechanical energy average value, the first historical data obtain module 1 include number acquiring unit 6, ratio calculation unit 7, Judging unit 8, target time section acquiring unit 9 and historical data acquiring unit 10.

Number acquiring unit 6 for obtaining elevator car door system in the total degree of the inward swinging door of history preset time period or shutdown, And holding duration meets first number of enabling or the shutdown of preset duration range；

Wherein, history preset time period is as unit of day.

Ratio calculation unit 7 is used to calculate the ratio of first number and total degree；

Judging unit 8 is for judging ratio whether more than the first given threshold, if being more than, it is determined that preset time period is History intermediary time period；

Target time section acquiring unit 9 is used to be obtained according to the corresponding mechanical energy average value of each history intermediary time period History target time section；

Specifically, target time section acquiring unit is used to put down the corresponding mechanical energy of each history intermediary time period Mean value is ranked up according to size, and corresponding history intermediary time period is as history target when choosing mechanical energy average value minimum Period；

Wherein, the health degree of the operating status of the size and elevator car door system of mechanical energy average value is negatively correlated.

Historical data acquiring unit 10 is used for the corresponding operation data of sampling time point each in history target time section Corresponding first history data when as in normal operating condition, i.e., based on original no label history data Automatic-searching orients the normal condition data in the history samples period.

As shown in fig. 7, the health evaluation system of the present embodiment further includes that fisrt feature matrix obtains module 11 and the second spy It levies matrix and obtains module 12.

Fisrt feature matrix obtains module 11 and is used to obtain corresponding first data square according to the first history data Battle array, and the first data matrix is standardized, obtain fisrt feature matrix；

Second characteristic matrix obtains module 12 and is used to obtain corresponding second data matrix according to current operating data, and Second data matrix is standardized, second characteristic matrix is obtained；

Wherein, corresponding to sampling time point each in each sampling time section in conjunction with expertise and feature extraction algorithm All operation datas carry out feature extraction and Feature Conversion processing, retain setting quantity characteristic parameter, such as following 15 spies Sign parameter: Q shaft current adds up electric energy, D shaft current adds up the sum of electric energy, velocity error, (velocity error square and velocity error The position of the positive maximum value appearance of the positive maximum value of the ratio of count value, velocity error, the negative maximum value of velocity error, velocity error, speed The position of degree error minus maximum value appearance, currently terminates the sum of initial position, Iq positive value, Iq negative value at current state initial position The sum of, the sum of Id positive value, the sum of Id negative value, mechanical energy average value etc..

The operating status for obtaining elevator car door system in the history samples period is one day most normal, and obtains in this day The first data matrix X1 of each corresponding operation data (15 characteristic parameters) formation of sampling time point；When obtaining present sample Between in section corresponding operation data (the 15 characteristic parameters) current operating data of each sampling time point form the second data matrix X2；

First data matrix X1 and the second data matrix X2 are standardized, respectively obtain corresponding One eigenmatrix and second characteristic matrix are specifically standardized using following formula:

X=(X- μ)/σ

Wherein, x indicates that fisrt feature matrix or second characteristic matrix, X indicate the first data matrix or the second data square Battle array, μ indicate that average vector, σ indicate covariance matrix.

Model obtains module 3 and is used to be input to respectively using fisrt feature matrix and second characteristic matrix as training parameter Object module is trained, and is obtained the first object model for characterizing the normal operation of elevator car door system and is used for table Levy the second object module of the current operating situation of elevator car door system.

When object module includes gauss hybrid models, first object model is the first gauss hybrid models, the second target Model is the second gauss hybrid models；Wherein, object module can also include that other any can be realized for characterizing elevator door The model of the operating condition of system.

First registration obtains module 4 for calculating according to the first gauss hybrid models and the second gauss hybrid models To the first registration between current operating conditions and normal operating condition.

Specifically, the first gauss hybrid models or the second gauss hybrid models include:

Wherein, g (x) indicates the first gauss hybrid models or the second gauss hybrid models, h (x；θ_i) indicate single Gaussian function Number, x indicate that d dimension fisrt feature matrix or second characteristic matrix, I indicate mixed model quantity, p_iIndicate preset i-th single high The prioritized vector of this function meetsθ_iIndicate the model parameter of i-th of single Gaussian function, model parameter packet Include average vector μ_iWith covariance matrix σ_i。

Specifically, using EM (expectation maximization) algorithm to parameter θ_iEstimated, specific solution procedure is as follows:

(1) random initializtion model parameter θ；

(2) Bayes' theorem is used, data characteristics vector x is used_nIt is general with the posteriority of "current" model parameter θ computation model i Rate, specific formula is as follows:

(3) the maximum likelihood revaluation of model coefficient

By repeating step (2) and step (3) in an iterative process, calculating converges to a stable solution, the stable solution pair Maximum likelihood solution is answered, and then obtains convergent mean value, covariance matrix and preposition vector.

In addition, the selection of mixed model quantity I is come using BIC (Bayesian Information) criterion algorithm in gauss hybrid models It determines, specific formula is as follows:

Wherein, H_jIndicate that j-th candidates model, D indicate training characteristics；

Indicate that the max log likelihood function of j-th candidates model, k indicate the number for being estimated parameter Word, n indicates the size of feature, final to establish the best gauss hybrid models (i.e. first for having minimum bayesian information criterion score Gauss hybrid models) g₁(x), which is the model of most accurate characterization elevator door normal operation.

First registration obtains module 4 and calculates the first registration using following formula:

Wherein, CV indicates the first registration, g₁(x1) the first gauss hybrid models, g are indicated₂(x2) indicate that the second Gauss is mixed Molding type, x1 indicate that fisrt feature matrix, x2 indicate second characteristic matrix.

CV value range is 0-1, and the CV value is higher, then it represents that the current operating situation of elevator car door system is closer to normal State；Conversely, the CV value is lower, then it represents that the current operating situation of elevator car door system is further away from normal condition, it may occur however that certain It is a little to degenerate, need real-time maintenance measure appropriate.

In the present embodiment, by establishing for characterizing the first gauss hybrid models model of normal operation and being used for Characterize the second gauss hybrid models model of current operating situation, so obtain current operating conditions and normal operating condition it Between the first registration, according to first registration assess elevator car door system the corresponding health degree of current operating situation, knot Multidimensional data is closed, more comprehensive monitoring and analysis are realized, to improve the assessment accuracy of the health status of elevator car door system； And without label data (being not necessarily to manual intervention), to reduce cost of labor.

Embodiment 6

As shown in figure 8, the health evaluation system of the elevator car door system of the present embodiment is the further improvement to embodiment 5, Specifically:

The health evaluation system of the present embodiment obtains module 14, third for label presetting module 13, the second historical data Historical data obtains module 15, third feature matrix obtains module 16, fourth feature matrix obtains module 17, the second registration Obtain module 18, third registration obtains module 19, early warning value setting module 20, filtering processing module 21, the first warning information Generation module 22 and the second warning information generation module 23.

Label presetting module 13 is used to preset the operation of sub-health state and malfunction in the history samples period respectively Corresponding first label of data and the second label；Wherein, preset label process be by sub-health state, malfunction with it is right The process of corresponding relationship is set between the operation data answered.

Sub-health state includes but is not limited to the case where slider wear, guide rail cause frictional force to increase there are foreign matter.

Malfunction includes but is not limited to that switch gate is not in place, gate does not drive hall door, rail friction acutely to cause to switch The case where door velocity anomaly.

Second historical data obtains module 14 and is used to correspond to inferior health according in the first label acquisition history samples period Second history data of state；

Third historical data obtains module 15 and is used to correspond to failure shape according in the second label acquisition history samples period The third history data of state；

Wherein, the second history data, third history data include but is not limited to gate-control signal data, electricity Flow data, energy data, power data and speed data.

Third feature matrix obtains module 16 and is used for according to the corresponding third data matrix of the second history data, and Third data matrix is standardized, third feature matrix is obtained；

Fourth feature matrix obtains module 17 and is used to obtain corresponding 4th data square according to third history data Battle array, and the 4th data matrix is standardized, obtain fourth feature matrix；

Model obtains module 3 and is also used to be input to gauss hybrid models progress using third feature matrix as training parameter Training, obtains the third gauss hybrid models for characterizing elevator car door system operating condition under sub-health state；

Model obtains module 3 and is also used to be input to gauss hybrid models progress using fourth feature matrix as training parameter Training is obtained and is nonserviceabled the 4th gauss hybrid models of lower operating condition for characterizing elevator car door system；

Second registration obtains module 18 for calculating according to the first gauss hybrid models and third gauss hybrid models To the second registration between sub-health state and normal operating condition；

Third registration obtains module 19 for calculating according to the first gauss hybrid models and the 4th gauss hybrid models To the third registration between malfunction and normal operating condition；

Early warning value setting module 20 is used to set the first early warning value according to the maximum value in multiple second registrations；

Wherein, the case where enabling or shutdown function of first early warning value for early warning elevator car door system reduce；

Early warning value setting module is also used to set the second early warning value according to the maximum value in multiple third registrations；

Wherein, there is a situation where enablings or shutdown failure for early warning elevator car door system for the second early warning value.

Specifically, the corresponding third gauss hybrid models of each sampling time point under sub-health state:

g_u1(x_u1)、g_u2(x_u2)···

According to each third gauss hybrid models and the first gauss hybrid models calculate separately to obtain sub-health state with just Multiple second registrations between normal operating status:

CV_u1,CV_u2····

Corresponding 4th gauss hybrid models of each sampling time point under malfunction:

g_d1(x_d1)、g_d2(x_d2)···

Calculate separately to obtain malfunction and normal according to each 4th gauss hybrid models and the first gauss hybrid models Multiple third registrations between operating status:

CV_d1,CV_d2···

CV_T1=max (CV_d1,CV_d2······)

CV_T2=max (CV_u1,CV_u2······)

According to CV_T1The first early warning value is determined, according to CV_T2Determine the second early warning value.

Module 21 is filtered to be used to carry out the first registration using the sliding window of the first width and the second width Value filtering processing obtains corresponding 4th registration of each sampling time point and the 5th registration in the present sample period；

Wherein, the first width corresponds to long period, and the second width corresponds to short cycle；

First warning information generation module 22 is used to work as the 4th registration less than the first early warning value, and the 5th registration is big When the second early warning value, then generates enabling or shutdown function for characterizing elevator car door system reduce first and accuse Alert information；

Second warning information generation module 23 is used for when the 5th registration is less than the second early warning value, is generated for characterizing Second warning information of enabling or shutdown failure occurs for elevator car door system.

Analyze to obtain the feelings that enabling or shutdown failure occur for elevator car door system under sub-health state by the 4th registration Condition；Analyze to obtain the feelings that enabling or the reduction of shutdown function of elevator car door system occur under malfunction by the 5th registration Condition, to be alerted in time, in order to which personnel carry out malfunction elimination and processing in time.

Illustrate below with reference to specific example:

1) elevator car door system daily corresponding operation data within half a year in past is obtained, feature is carried out to operation data and is mentioned It takes and Feature Conversion, retains 15 characteristic parameters；

2) it obtains the open the door daily holding duration of total degree and door opening process of elevator car door system and is equal to preset duration (such as 377) door opening times；

3) ratio for calculating door opening times and total degree chooses every day on the corresponding date that ratio is greater than 95%, then Each mechanical energy average value corresponding to these days is ranked up, and is chosen mechanical energy average value the smallest one day and is used as mechanical energy Average value ran one day most normal within half a year in past, it is assumed that is 2019-03-12, it is each to obtain this day 2019-03-12 The corresponding time series of sampling time point (i.e. the first data matrix) X1；

4) corresponding second data of each sampling time point in the present sample period under current operating conditions are obtained Matrix X2；

5) the first data matrix X1 and the second data matrix X2 are standardized, are respectively obtained corresponding Fisrt feature matrix x1 and second characteristic matrix x2；

6) Gaussian Mixture mould is input to using fisrt feature matrix x1 and second characteristic matrix x2 as training parameter respectively Type is trained, and obtains the first gauss hybrid models g for characterizing the normal operation of elevator car door system₁(x1) it and uses In the second gauss hybrid models g of the current operating situation of characterization elevator car door system₂(x2)。

7) according to the first gauss hybrid models g₁(x1) and the second gauss hybrid models g₂(x2) current operation is calculated The first registration CV between state and normal operating condition, such as obtain corresponding first weight of current a certain sampling time point Right CV=0.5932.

Obtain elevator car door system third gauss hybrid models of operating condition and its corresponding multiple under sub-health state Second registration:

g_u1(x_u1)、g_u2(x_u2)···；CV_u1,CV_u2····

Elevator car door system is obtained to nonserviceable the 4th gauss hybrid models of lower operating condition:

g_d1(x_d1)、g_d2(x_d2)···；CV_d1,CV_d2···

CV_T1=max (CV_d1,CV_d2)=0.2541；

CV_T2=max (CV_u1,CV_u2)=0.7806；

According to CV_T1Determine that the first early warning value is 0.3, according to CV_T2Determine that the second early warning value is 0.8.

8) different in width (n is used to the corresponding first registration CV of each sampling time point in the present sample period =5 and n=500) mean filter is filtered and obtains corresponding 4th registration CV_SAnd CV_L；

9) work as CV_LLess than 0.8 and CV_SWhen more than or equal to 0.3, then generate for characterize elevator car door system enabling or The first warning information that shutdown function reduces；Work as CV_SWhen less than 0.3, then generate for characterize elevator car door system occur open the door or Second warning information of shutdown failure.

In addition, the evaluation process of the health status of the door closing procedure of elevator car door system is similar to the strong of above-mentioned door opening process The evaluation process of health state, therefore be not described in more detail here.

In the present embodiment, by establishing for characterizing the first gauss hybrid models model of normal operation and being used for Characterize the second gauss hybrid models model of current operating situation, so obtain current operating conditions and normal operating condition it Between the first registration, according to first registration assess elevator car door system the corresponding health degree of current operating situation, knot Multidimensional data is closed, more comprehensive monitoring and analysis are realized, to improve the assessment accuracy of the health status of elevator car door system； And without label data (being not necessarily to manual intervention), to reduce cost of labor；Additionally, it is provided the health of elevator car door system State alarming mechanism can remind in time user or maintenance personal to carry out maintenance measure appropriate in advance to elevator door, and then keep away Exempt from elevator door to break down.

Embodiment 7

Fig. 9 is the structural schematic diagram for a kind of electronic equipment that the embodiment of the present invention 7 provides.Electronic equipment include memory, Processor and storage are on a memory and the computer program that can run on a processor, processor realize reality when executing program Apply the health evaluating method of the elevator car door system in example 1 to 3 in any one embodiment.The electronic equipment 30 that Fig. 9 is shown is only One example, should not function to the embodiment of the present invention and use scope bring any restrictions.

As shown in figure 9, electronic equipment 30 can be showed in the form of universal computing device, such as it can be server Equipment.The component of electronic equipment 30 can include but is not limited to: at least one above-mentioned processor 31, at least one above-mentioned storage Device 32, the bus 33 for connecting different system components (including memory 32 and processor 31).

Bus 33 includes data/address bus, address bus and control bus.

Memory 32 may include volatile memory, such as random access memory (RAM) 321 and/or cache Memory 322 can further include read-only memory (ROM) 323.

Memory 32 can also include program/utility 325 with one group of (at least one) program module 324, this The program module 324 of sample includes but is not limited to: operating system, one or more application program, other program modules and journey It may include the realization of network environment in ordinal number evidence, each of these examples or certain combination.

Processor 31 by operation storage computer program in memory 32, thereby executing various function application with And the health evaluating method of the elevator car door system in data processing, such as the embodiment of the present invention 1 to 3 in any one embodiment.

Electronic equipment 30 can also be communicated with one or more external equipments 34 (such as keyboard, sensing equipment etc.).It is this Communication can be carried out by input/output (I/O) interface 35.Also, the equipment 30 that model generates can also pass through Network adaptation Device 36 and one or more network (such as local area network (LAN), wide area network (WAN) and/or public network, such as internet) Communication.As shown in figure 9, the other modules for the equipment 30 that network adapter 36 is generated by bus 33 and model communicate.It should be bright It is white, although not shown in the drawings, the equipment 30 that can be generated with binding model uses other hardware and/or software module, including but not Be limited to: microcode, device driver, redundant processor, external disk drive array, RAID (disk array) system, tape drive Dynamic device and data backup storage system etc..

It should be noted that although be referred in the above detailed description electronic equipment several units/modules or subelement/ Module, but it is this division be only exemplary it is not enforceable.In fact, embodiment according to the present invention, above The feature and function of two or more units/modules of description can embody in a units/modules.Conversely, retouching above The feature and function for the units/modules stated can be to be embodied by multiple units/modules with further division.

Embodiment 8

A kind of computer readable storage medium is present embodiments provided, computer program is stored thereon with, program is processed The step in the health evaluating method of the elevator car door system in embodiment 1 to 3 in any one embodiment is realized when device executes.

Wherein, what readable storage medium storing program for executing can use more specifically can include but is not limited to: portable disc, hard disk, random Access memory, read-only memory, erasable programmable read only memory, light storage device, magnetic memory device or above-mentioned times The suitable combination of meaning.

In possible embodiment, the present invention is also implemented as a kind of form of program product comprising program generation Code, when program product is run on the terminal device, program code is appointed for executing terminal device in realization embodiment 1 to 3 Step in the health evaluating method of elevator car door system in an embodiment of anticipating.

Wherein it is possible to be write with any combination of one or more programming languages for executing journey of the invention Sequence code, program code can be executed fully in viewer apparatus, partly execute in viewer apparatus, is only as one Vertical software package executes, partially part executes on a remote device or executes on a remote device completely in viewer apparatus.

Although specific embodiments of the present invention have been described above, it will be appreciated by those of skill in the art that this is only For example, protection scope of the present invention is to be defined by the appended claims.Those skilled in the art without departing substantially from Under the premise of the principle and substance of the present invention, many changes and modifications may be made, but these change and Modification each falls within protection scope of the present invention.

Claims (22)

1. a kind of health evaluating method of elevator car door system, which is characterized in that the health evaluating method includes:

S1. it obtains elevator car door system and is in corresponding first history run number when normal operating condition within the history samples period According to；

S2. the current operating data in the present sample period of the elevator car door system in the current state of operation is obtained；

S3. target mould is input to using first history data and the current operating data as training parameter respectively Type is trained, and is obtained for characterizing the first object model of the normal operation of the elevator car door system and for characterizing State the second object module of the current operating situation of elevator car door system；

S4. the current operating conditions and the normal fortune are obtained according to the first object model and second object module The first registration between row state；

S5. the corresponding health degree of current operating situation of the elevator car door system is determined according to first registration；

Wherein, first registration is positively correlated with the health degree.

2. the health evaluating method of elevator car door system as described in claim 1, which is characterized in that when the object module includes When gauss hybrid models, the first object model is the first gauss hybrid models, and second object module is the second Gauss Mixed model；

Step S4 includes:

S41. the current operation shape is calculated according to first gauss hybrid models and second gauss hybrid models The first registration between state and the normal operating condition.

3. the health evaluating method of elevator car door system as claimed in claim 2, which is characterized in that when first history run When data include the holding duration of door opening process or the holding duration of door closing procedure and mechanical energy average value, step S1 is specific Include:

S11. the elevator car door system is obtained in the total degree and the holding of the inward swinging door of history preset time period or shutdown First number of long enabling or the shutdown for meeting preset duration range；

S12. the ratio of first number and the total degree is calculated；

S13. the ratio is judged whether more than the first given threshold, if being more than, it is determined that the preset time period is in history Between the period；

S14. history target time section is obtained according to the corresponding mechanical energy average value of each history intermediary time period；

S15. using the corresponding operation data of sampling time point each in the history target time section as in normal operation shape Corresponding first history data when state.

4. the health evaluating method of elevator car door system as claimed in claim 3, which is characterized in that step S14 includes:

The corresponding mechanical energy average value of each history intermediary time period is ranked up according to size, chooses the mechanical energy Corresponding history intermediary time period is as the history target time section when average value minimum；

Wherein, the health degree of the operating status of the size and elevator car door system of the mechanical energy average value is in negative It closes；And/or

The history preset time period is as unit of day.

5. the health evaluating method of elevator car door system as claimed in claim 3, which is characterized in that after step S15, step S3 Before further include:

Corresponding first data matrix is obtained according to first history data；

First data matrix is standardized, fisrt feature matrix is obtained；

Corresponding second data matrix is obtained according to the current operating data；

Second data matrix is standardized, second characteristic matrix is obtained；

Step S3 further include:

Respectively using the fisrt feature matrix and the second characteristic matrix as training parameter, be input to the object module into Row training, obtains for characterizing the first object model of the normal operation of the elevator car door system and for characterizing the electricity Second object module of the current operating situation of terraced door system.

6. the health evaluating method of elevator car door system as claimed in claim 5, which is characterized in that the first Gaussian Mixture mould Type or second gauss hybrid models include:

Wherein, g (x) indicates first gauss hybrid models or second gauss hybrid models, h (x；θ_i) indicate single Gauss Function, x indicate that d ties up the fisrt feature matrix or the second characteristic matrix, and I indicates mixed model quantity, p_iIndicate default I-th of single Gaussian function prioritized vector, meetθ_iIndicate the model parameter of i-th of single Gaussian function, The model parameter includes average vector μ_iWith covariance matrix σ_i。

7. the health evaluating method of elevator car door system as claimed in claim 6, which is characterized in that using as follows in step S41 Formula calculates first registration:

Wherein, CV indicates first registration, g₁(x1) first gauss hybrid models, g are indicated₂(x2) described the is indicated Two gauss hybrid models, x1 indicate that the fisrt feature matrix, x2 indicate the second characteristic matrix.

8. the health evaluating method of elevator car door system as claimed in claim 3, which is characterized in that the health evaluating method is also Include:

Corresponding first label of the operation data of sub-health state and malfunction in the history samples period is preset respectively With the second label；

After step S5 further include:

The second history data that sub-health state is corresponded in the history samples period is obtained according to first label；

The third history data that malfunction is corresponded in the history samples period is obtained according to second label；

According to the corresponding third data matrix of second history data；

The third data matrix is standardized, third feature matrix is obtained；

Corresponding 4th data matrix is obtained according to the third history data；

4th data matrix is standardized, fourth feature matrix is obtained；

It using the third feature matrix as training parameter, is input to gauss hybrid models and is trained, obtain for characterizing State the third gauss hybrid models of elevator car door system operating condition under sub-health state；

It using the fourth feature matrix as training parameter, is input to gauss hybrid models and is trained, obtain for characterizing Elevator car door system is stated to nonserviceable the 4th gauss hybrid models of lower operating condition；

The sub-health state and institute is calculated according to first gauss hybrid models and the third gauss hybrid models State the second registration between normal operating condition；

According to first gauss hybrid models and the 4th gauss hybrid models be calculated the malfunction with it is described Third registration between normal operating condition；

The first early warning value is set according to the maximum value in multiple second registrations；

Wherein, the case where enabling or shutdown function of first early warning value for elevator car door system described in early warning reduce；

The second early warning value is set according to the maximum value in multiple third registrations；

Wherein, there is a situation where enablings or shutdown failure for elevator car door system described in early warning for second early warning value.

9. the health evaluating method of elevator car door system as claimed in claim 8, which is characterized in that the health evaluating method is also Include:

Mean filter processing is carried out to first registration using the sliding window of the first width and the second width, described in acquisition Corresponding 4th registration of each sampling time point and the 5th registration in the present sample period；

Wherein, first width corresponds to long period, and second width corresponds to short cycle；

When the 4th registration be less than first early warning value, and the 5th registration be greater than or equal to second early warning When value, then the first warning information that enabling or shutdown function for characterizing the elevator car door system reduce is generated；

When the 5th registration is less than second early warning value, generate for characterize the elevator car door system occur to open the door or Second warning information of shutdown failure.

10. the health evaluating method of elevator car door system as claimed in claim 8, which is characterized in that first history run Data, second history data, the third history data, the current operating data include gate-control signal At least one of data, current data, energy data, power data and speed data.

11. a kind of health evaluation system of elevator car door system, which is characterized in that the health evaluation system includes the first history number According to obtaining, module, current data acquisition module, model obtains module, the first registration obtains module and health degree determines mould Block；

First historical data obtains module for obtaining elevator car door system within the history samples period in normal operation Corresponding first history data when state；

The current data obtains module for obtaining the present sample time of the elevator car door system in the current state of operation Current operating data in section；

The model obtains module for respectively using first history data and the current operating data as training Parameter is input to object module and is trained, and obtains the first mesh for characterizing the normal operation of the elevator car door system Mark the second object module of model and the current operating situation for characterizing the elevator car door system；

First registration obtains module and is used for according to the first object model and second object module acquisition The first registration between current operating conditions and the normal operating condition；

The health degree determining module is used to determine the current operation feelings of the elevator car door system according to first registration The corresponding health degree of condition；

Wherein, first registration is positively correlated with the health degree.

12. the health evaluation system of elevator car door system as claimed in claim 11, which is characterized in that when the object module packet When including gauss hybrid models, the first object model is the first gauss hybrid models, and second object module is second high This mixed model；

First registration obtains module and is used for according to first gauss hybrid models and second gauss hybrid models The first registration between the current operating conditions and the normal operating condition is calculated.

13. the health evaluation system of elevator car door system as claimed in claim 12, which is characterized in that when first history is transported When row data include the holding duration of door opening process or the holding duration of door closing procedure and mechanical energy average value, described first Historical data obtains module and includes number acquiring unit, ratio calculation unit, judging unit, target time section acquiring unit and go through History data capture unit；

The number acquiring unit is used to obtain the elevator car door system at total time of the inward swinging door of history preset time period or shutdown First number of several and described enabling or the shutdown for keeping duration to meet preset duration range；

The ratio calculation unit is used to calculate the ratio of first number and the total degree；

The judging unit is for judging the ratio whether more than the first given threshold, if being more than, it is determined that when described default Between section be history intermediary time period；

The target time section acquiring unit is used to be obtained according to the corresponding mechanical energy average value of each history intermediary time period Take history target time section；

The historical data acquiring unit is used for the corresponding operation number of sampling time point each in the history target time section Corresponding first history data when according to as in normal operating condition.

14. the health evaluation system of elevator car door system as claimed in claim 13, which is characterized in that the target time section obtains Take unit for the corresponding mechanical energy average value of each history intermediary time period to be ranked up according to size, described in selection Corresponding history intermediary time period is as the history target time section when mechanical energy average value minimum；

Wherein, the health degree of the operating status of the size and elevator car door system of the mechanical energy average value is in negative It closes；And/or

The history preset time period is as unit of day.

15. the health evaluation system of elevator car door system as claimed in claim 13, which is characterized in that the health evaluation system It further include that fisrt feature matrix obtains module and second characteristic matrix acquisition module；

The fisrt feature matrix obtains module and is used to obtain corresponding first data square according to first history data Battle array, and first data matrix is standardized, obtain fisrt feature matrix；

The second characteristic matrix obtains module and is used to obtain corresponding second data matrix according to the current operating data, and Second data matrix is standardized, second characteristic matrix is obtained；

The model obtains module for respectively using the fisrt feature matrix and the second characteristic matrix as training parameter, It is input to the object module to be trained, obtains the first object for characterizing the normal operation of the elevator car door system Second object module of model and the current operating situation for characterizing the elevator car door system.

16. the health evaluation system of elevator car door system as claimed in claim 5, which is characterized in that first Gaussian Mixture Model or second gauss hybrid models include:

Wherein, g (x) indicates first gauss hybrid models or second gauss hybrid models, h (x；θ_i) indicate single Gauss Function, x indicate that d ties up the fisrt feature matrix or the second characteristic matrix, and I indicates mixed model quantity, p_iIndicate default I-th of single Gaussian function prioritized vector, meetθ_iIndicate the model parameter of i-th of single Gaussian function, The model parameter includes average vector μ_iWith covariance matrix σ_i。

17. the health evaluation system of elevator car door system as claimed in claim 16, which is characterized in that first registration obtains Modulus block calculates first registration using following formula:

Wherein, CV indicates first registration, g₁(x1) first gauss hybrid models, g are indicated₂(x2) described the is indicated Two gauss hybrid models, x1 indicate that the fisrt feature matrix, x2 indicate the second characteristic matrix.

18. the health evaluation system of elevator car door system as claimed in claim 13, which is characterized in that the health evaluation system Module is obtained for label presetting module, the second historical data, third historical data obtains module, third feature matrix obtains mould Block, fourth feature matrix obtain module, the second registration obtains module, third registration obtains module and early warning value sets mould Block；

The label presetting module is used to preset the fortune of sub-health state and malfunction in the history samples period respectively Corresponding first label of row data and the second label；

Second historical data obtains module and is used for according to corresponding in first label acquisition history samples period Second history data of sub-health state；

The third historical data obtains module and is used for according to corresponding in second label acquisition history samples period The third history data of malfunction；

The third feature matrix obtains module and is used for according to the corresponding third data matrix of second history data, and The third data matrix is standardized, third feature matrix is obtained；

The fourth feature matrix obtains module and is used to obtain corresponding 4th data square according to the third history data Battle array, and the 4th data matrix is standardized, obtain fourth feature matrix；

The model obtains module and is also used to using the third feature matrix as training parameter, be input to gauss hybrid models into Row training, obtains the third gauss hybrid models for characterizing elevator car door system operating condition under sub-health state；

The model obtains module and is also used to using the fourth feature matrix as training parameter, be input to gauss hybrid models into Row training is obtained and is nonserviceabled the 4th gauss hybrid models of lower operating condition for characterizing the elevator car door system；

Second registration obtains module and is used for according to first gauss hybrid models and the third gauss hybrid models The second registration between the sub-health state and the normal operating condition is calculated；

The third registration obtains module and is used for according to first gauss hybrid models and the 4th gauss hybrid models The third registration between the malfunction and the normal operating condition is calculated；

The early warning value setting module is used to set the first early warning value according to the maximum value in multiple second registrations；

Wherein, the case where enabling or shutdown function of first early warning value for elevator car door system described in early warning reduce；

The early warning value setting module is also used to set the second early warning value according to the maximum value in multiple third registrations；

Wherein, there is a situation where enablings or shutdown failure for elevator car door system described in early warning for second early warning value.

19. the health evaluation system of elevator car door system as claimed in claim 18, which is characterized in that the health evaluation system Including filtering processing module, the first warning information generation module and the second warning information generation module；

The filtering processing module is used to carry out first registration using the sliding window of the first width and the second width Mean filter processing obtains corresponding 4th registration of each sampling time point in the present sample period and the 5th and is overlapped Degree；

Wherein, first width corresponds to long period, and second width corresponds to short cycle；

The first warning information generation module is used to be less than first early warning value, and the described 5th when the 4th registration When registration is greater than or equal to second early warning value, then enabling or the shutdown function for characterizing the elevator car door system are generated The first warning information that can be reduced；

The second warning information generation module is used for when the 5th registration is less than second early warning value, and generation is used for Characterize the second warning information that enabling or shutdown failure occur for the elevator car door system.

20. the health evaluation system of elevator car door system as claimed in claim 18, which is characterized in that first history run Data, second history data, the third history data, the current operating data include gate-control signal At least one of data, current data, energy data, power data and speed data.

21. a kind of electronic equipment including memory, processor and stores the calculating that can be run on a memory and on a processor Machine program, which is characterized in that the processor realizes electricity of any of claims 1-10 when executing computer program The health evaluating method of terraced door system.

22. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program The step of health evaluating method of elevator car door system of any of claims 1-10 is realized when being executed by processor.